paper-with-me

홈 › Papers

Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations

2025-06-12 · Shijie Fang, Hang Yu, Qidi Fang, Reuben M. Aronson, Elaine S. Short

Learning from Demonstration (LfD) is a popular approach for robots to acquire new skills, but most LfD methods suffer from imperfections in human demonstrations. Prior work typically treats these suboptimalities as random noise. In this paper we study non-optimal behaviors in non-expert demonstrations and show that they are systematic, forming what we call demonstration sidetracks. Using a public space study with 40 participants performing a long-horizon robot task, we recreated the setup in simulation and annotated all demonstrations. We identify four types of sidetracks (Exploration, Mistake, Alignment, Pause) and one control pattern (one-dimension control). Sidetracks appear frequently across participants, and their temporal and spatial distribution is tied to task context. We also find that users' control patterns depend on the control interface. These insights point to the need for better models of suboptimal demonstrations to improve LfD algorithms and bridge the gap between lab training and real-world deployment. All demonstrations, infrastructure, and annotations are available at https://github.com/AABL-Lab/Human-Demonstration-Sidetracks.

📄 PDF Abstract BibTeX arXiv:2506.11262

Code (1)

aabl-lab/human-demonstration-sidetracks 공식 구현

Similar Papers 제목 키워드 기반

Towards Sample-efficient Apprenticeship Learning from Suboptimal Demonstration

2021-10-08 · Letian Chen, Rohan Paleja, Matthew Gombolay

Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform novel tasks by providing demonstrations. However, as demonstrators are typically non-experts…

Inverse Reinforcement Learning via Matching of Optimality Profiles

2020-11-18 · Luis Haug, Ivan Ovinnikov, Eugene Bykovets

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality

2021-10-27 · NeurIPS 2021 12 · Songyuan Zhang, Zhangjie Cao, Dorsa Sadigh, Yanan Sui

Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a …

Imitation Learning

Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations

2023-06-13 · Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang 외

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a lar…

Decision MakingDisentanglementImitation LearningSequential Decision Making

The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

2022-04-22 · ICLR 2022 4 · Cassidy Laidlaw, Anca Dragan

Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for…

Bayesian InferenceImitation Learning